Feature-based speech recognizer having probabilistic linguistic

Details Feature-based speech recognizer having probabilistic linguistic Feature-based speech recognizer having probabilistic linguistic

1996-06-05

1998-10-13

Hudspeth, David R.

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

704240, 704243, 704253, G10L 506

Patent

active

058227296

ABSTRACT:
A feature-based speech recognizer having a probabilistic linguistic processor provides word matching based on the entire space of feature vectors. In this manner, the errors and inaccuracies associated with the heretofore known feature-based speech recognizers, which provided word matching on less than the entire space of feature vectors, are overcome, thereby resulting in improved-accuracy speech recognition. The word matching may be on feature vectors computed either from segments or from landmarks or from both segments and landmarks. For word matching on segment-based feature vectors, acoustic likelihoods may be normalized by extra-acoustic likelihoods defined by at least one extra-acoustic ("not" or "anti") model. Context-dependent and context-independent acoustic models may be employed.

REFERENCES:
Mari Ostendorf, Vassilios V. Digalakis, and Owen A. Kimball, "From HMM's to Segment Models: A Unified View of Stochastic Modeling for Speech Recognition", IEEE Trans. on Speech and Audio Processing, vol. 4, No. 5, pp. 360-378, Sep. 1996.
James Glass, Jane Chang, and Michael McCandless, "A Probabilistic Framework for Feature-Based Speech Recognition", Proceedings of the Fourth International Conference on Spoken Language Processing (ICSLP 96), pp. 2277-2280, Oct. 1996.
Zue et al., "Recent progress on the SUMMIT system," Proc. Speech and Natural Language Workshop, pp. 380-384 (Jun. 1990).
Digilakis et al., "ML estimation of a stochastic linear system with the EM algorithm and its application to speech recognition," IEEE Trans. Speech and Audio Processing, 1(4):431-442 (Oct. 1993).
Anonymous, "Boundary Detection for Addword through Decoding," IBM Technical Disclosue Bulletin, vol. 36, No. 3, pp. 47-48 (Mar., 1993).
Vidal et al., "A review and New Approaches for Automatic Segmentation Of Speech Signals," vol. 1, Proceedings Of Eusipco-90 Fifth European Signal Processing Conference, pp. 43-53, (Sep., 1990).
Lamel et al., "High Performance speaker-independent phone recognition using CDHMM," Proc. ICASSP, pp. 447-450, (May 1996).
Mari et al., "A second-order HMM for high performance word and phoneme-based continuous speech recognition," Proc. ICASSP, pp. 435-438 (May 1996).
Robinson, "An application of recurrent nets to phone probability estimates," IEEE Trans. Neural Networks, 5(2):298-305 (Mar. 1994).
Marcus, "Phonetic recognition in a segment-based HMM," Proc. ICASSP, pp. 479-482 (Apr. 1993).
Digilakis et al,. "ML estimation of a stochastic linear system with the EM algorithm and its application to speech recognition," IEEE Trans. Speech and Audio Processing, 1(4):431-442 (Oct. 1993).
Holmes et al., "Modeling speech variability with segmental HMMs," Proc. ICASSP, pp. 447-450 (May 1996).
Ljolje et al., "High accuracy phone recognition using context clustering and quasi-triphone models," Computer Speech and Language, 8(2):129-151 (Apr. 1994).
Roucos et al., "Stochastic segment modeling using the Estimate-Maximize algorithm," Proc. ICASSP, pp. 127-130 (1988).
Goldenthal, "Statistical trajectory models for phonetic recognition," Technical report MIT/LCS/TR-642, MIT Lab. for Computer Science (Aug. 1994).
Leung et al., "Speech recognition using stochastic segment neural networks," Proc. ICASSP, pp. 613-616 (Mar. 1992).
Ostendorf and Roucos, "A stochastic segment model for phenome-based continuous speech recognition," IEEE Trans. ASSP, 37(12):1857-1869 (Dec. 1989).
Rohlicek et al., "Continuous hidden Markov modelling for speaker-independent word spotting," Proc. ICASSP, pp. 627-630 (May 1989).
Rose et al., "A hidden Markov model based keyword recognition system," Proc. ICASSP, pp. 129-132 (Apr. 1990).
Wilpon et al., "Automatic recognition of keywords in unconstrained speech using hidden Markov models," IEEE Trans. ASSP, 38(11):1870-1878 (Nov. 1990).
Cohen, "Segmenting speech using dynamic programming," Journal of the Acoustic Society of America, 69(5):1430-1438 (May 1981).

Affiliated with

Also associated with

Rating

Feature-based speech recognizer having probabilistic linguistic does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Feature-based speech recognizer having probabilistic linguistic , we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Feature-based speech recognizer having probabilistic linguistic will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-326888